Collection of object models compatible with pybullet simulator https://github.com/bulletphysics/bullet3/tree/master/examples/pybullet
-
Updated
Jun 5, 2020 - Python
Collection of object models compatible with pybullet simulator https://github.com/bulletphysics/bullet3/tree/master/examples/pybullet
Denoising YCB Objects with a self-supervised deep neural network
Final Project for the course "Intelligent Robotic Manipulation" (WiSe 2024/25) at TU Darmstadt
Benchmarking parallel simulations on pybullet.
Fine-tuned **YOLO26n-seg** model for segmenting YCB objects in images or video. Trained on our own annotated data with YOLO26 augmentations, starting from a model pretrained on the YCB Berkeley dataset. Includes weights and validation figures.
How much visual variety does a simulator need before a model trained in it works on real photographs? Six ResNet-18 classifiers, 150,000 synthetic renders, 3,000 real YCB test images, zero real training data. Randomization takes accuracy from 8.6% to 61.3%, and Grad-CAM shows why: attention moves from background to object.
PointNet++ primitive-shape classification with APS-to-YCB synthetic-to-real generalisation and ModelNet40 evaluation.
To associate your repository with the ycb-objects topic, visit your repo's landing page and select "manage topics."